Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate awareness and acknowledgment of issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ikk
    -0.19
    uraa
    -0.15
    CompleteListener
    -0.15
    è¼Ŀ
    -0.15
     vere
    -0.15
    PRETTY
    -0.14
    ORM
    -0.14
    ãĥĮ
    -0.14
    etty
    -0.13
     зай
    -0.13
    POSITIVE LOGITS
    ÛĮÙĨÚ©
    0.15
    ัà¸į
    0.14
    908
    0.14
    egan
    0.14
    pt
    0.14
    berger
    0.14
    orses
    0.14
    èĥİ
    0.14
    764
    0.14
    FUN
    0.13
    Act Density 0.163%

    No Known Activations